Uploaded August 2026 | Updated September 2026, 3 weeks ago
AI researcher Stephen "Cas" Casper of the Harvard Kennedy School joins Robert Wright to discuss new developments in the OpenAI breakout story—including how the AI agents invented messaging workarounds to coordinate with each other and other spookiness. Plus: Which AI is the biggest shill for its maker?
Subscribe to The NonZero Newsletter at: nonzero.org/subscribe
Exclusive Overtime discussion: nonzero.org/p/the-openai-breakout-and-other-ai
Join NonZero's Discord server: discord.gg/Zy4jAhTQMF
Excerpt from Ch.11, "Hive Minds and the Loss of Control", of The God Test: thegodtest.net/chapter-11.html
0:00 Teaser
0:49 Stephen’s expertise in spooky AI behavior
3:51 Testing AIs for “corporate loyalty”
20:19 Which AIs shill most for their makers?
33:21 Do AI models have ideologies?
38:59 The spookiest finding of Stephen’s study
43:26 Are AIs getting better at gaming their tests?
50:25 Overtime unlocked: The OpenAI breakout
55:24 Decoding the OpenAI breakout
1:02:38 Did OpenAI’s agents evolve their own culture?
1:13:46 How OpenAI’s agents outfoxed their makers
Discussed in Overtime:
Stephen’s p-doom post-OpenAI-breakout.
Is safe AI possible in an arms race?
Stephen: AI safety is a (technically) solved problem.
The open source AI question(s).
A hopeful stat amid the spookiness.
Robert Wright (Nonzero, The Evolution of God, Why Buddhism Is True) and Stephen Casper (Harvard Kennedy School). Recorded August 26, 2026.
Twitter: twitter.com/NonzeroPods
AI researcher Stephen "Cas" Casper of the Harvard Kennedy School joins Robert Wright to discuss new developments in the OpenAI breakout story—including how the AI agents invented messaging workarounds to coordinate with each other and other spookiness. Plus: Which AI is the biggest shill for its maker?
Subscribe to The NonZero Newsletter at: nonzero.org/subscribe
Exclusive Overtime discussion: nonzero.org/p/the-openai-breakout-and-other-ai
Join NonZero's Discord server: discord.gg/Zy4jAhTQMF
Excerpt from Ch.11, "Hive Minds and the Loss of Control", of The God Test: thegodtest.net/chapter-11.html
0:00 Teaser
0:49 Stephen’s expertise in spooky AI behavior
3:51 Testing AIs for “corporate loyalty”
20:19 Which AIs shill most for their makers?
33:21 Do AI models have ideologies?
38:59 The spookiest finding of Stephen’s study
43:26 Are AIs getting better at gaming their tests?
50:25 Overtime unlocked: The OpenAI breakout
55:24 Decoding the OpenAI breakout
1:02:38 Did OpenAI’s agents evolve their own culture?
1:13:46 How OpenAI’s agents outfoxed their makers
Discussed in Overtime:
Stephen’s p-doom post-OpenAI-breakout.
Is safe AI possible in an arms race?
Stephen: AI safety is a (technically) solved problem.
The open source AI question(s).
A hopeful stat amid the spookiness.
Robert Wright (Nonzero, The Evolution of God, Why Buddhism Is True) and Stephen Casper (Harvard Kennedy School). Recorded August 26, 2026.
Twitter: twitter.com/NonzeroPods
